On Tue, Jul 28, 2020 at 05:09:50PM +, Yuying Zhang wrote:
> The ol_flags check lacks of flag for IPv6 which causes checksum
> flag configuration error while IPv6/TCP TSO packet is sent.
> This patch fixes the issue by adding PKT_TX_TCP_SEG flag.
Thanks Yuying for the new version. I have anothe
On 7/28/20 9:03 PM, Matan Azrad wrote:
>
>
> From: Maxime Coquelin:
>> At .new_device() time, only the first vring pair is now ready, other vrings
>> are
>> consfigured later.
>>
>> Problem is that when application will setup and enable interrupts, only the
>> first queue pair Rx interrupt wi
The ice needs the exact TCP header size including options for TCP
checksum offload, but according to PKT_TX_TCP_CKSUM note, l4_len
is not required to be set, so it needs to calculate the TCP header
size if not set.
Fixes: 17c7d0f9d6a4 ("net/ice: support basic Rx/Tx")
Cc: sta...@dpdk.org
Signed-of
> -Original Message-
> From: Wang, Haiyue
> Sent: Wednesday, July 29, 2020 3:51 PM
> To: dev@dpdk.org; Yang, Qiming ; Zhang, Qi Z
>
> Cc: Wang, Yinan ; Xu, Ting ;
> Wang, Haiyue ; sta...@dpdk.org
> Subject: [PATCH v1] net/ice: calculate TCP header size for offload
>
> The ice needs th
Hi, Phil
Very nice comment, I found it is useful, I'm on moving mlx5 PMD to use C11
atomic primitives, thank you.
But, don't you think it is an overkill for testpmd case and would make code
wordy and less readable ?
How does testpmd start the forwarding? Let's have a glance at
launch_packet_for
IANA has assigned port 6081 as the fixed well-known destination port for
GENEVE. Nevertheless draft-ietf-nvo3-geneve-09 recommends that
implementations make this configurable. This commit enables specifying
any positive UDP destination port number for GENEVE.
Signed-off-by: Ophir Munk
---
app/t
GENEVE is a widely used tunneling protocol in modern Virtualized
Networks. testpmd already supports parsing of several tunneling
protocols including VXLAN, VXLAN-GPE, GRE. This commit adds GENEVE
parsing of inner protocols (IPv4-0x0800, IPv6-0x86dd, Ethernet-0x6558)
based on IETF draft-ietf-nvo3-ge
This is a cleanup commit. It assembles all tunnel outer updates into one
function call to avoid code duplications.
It defines RTE_VXLAN_GPE_DEFAULT_PORT (4790) in accordance with all
other tunnel protocol definitions.
Signed-off-by: Ophir Munk
---
app/test-pmd/csumonly.c| 72 +---
This patchset adds GENEVE parsing of inner protocols (IPv4-0x0800, IPv6-0x86dd,
Ethernet-0x6558) based on IETF draft-ietf-nvo3-geneve-09.
v1:
Initial version
Ophir Munk (3):
app/testpmd: add GENEVE parsing
app/testpmd: enable configuring GENEVE port
app/testpmd: reduce tunnel parsing code d
Fix memory leak where variable oob_enable can go out of scope leaking
the storage it points to.
Coverity issue: 337674
Fixes: 95f648ff9ee ("examples/vm_power: make branch ratio threshold per core")
Signed-off-by: Rory Sexton
---
examples/vm_power_manager/main.c | 1 +
1 file changed, 1 insertio
Hi Maxime
From: Maxime Coquelin:
> On 7/28/20 9:03 PM, Matan Azrad wrote:
> >
> >
> > From: Maxime Coquelin:
> >> At .new_device() time, only the first vring pair is now ready, other
> >> vrings are consfigured later.
> >>
> >> Problem is that when application will setup and enable interrupts,
> >
Hi Stephen,
Our system has 2 sockets as seen from below :
[root@flexran3 dchitkara]# lscpu
Architecture: x86_64
CPU op-mode(s):32-bit, 64-bit
Byte Order:Little Endian
CPU(s):80
On-line CPU(s) list: 0-79
Thread(s) per core:2
Core(s) per socket:
Hi Team,
With fix suggest in prev mail thread at testpmd side, PDUMP works with testpmd.
However when we try to run our own primary app with PDUMP as a secondary
process, PDUMP console comes up, however it does not capture any packets.
Changes made at primary app side:
1. PDUMP initialised just
Hi Stephen,
If that was the case, then how come pdump worked with testpmd?
See below testpmd with pdumg log:
Testpmd:
[root@flexran3 x86_64-native-linux-icc]# ./app/testpmd -c 0xf0 -n 4 -- -i
--port-topology=chained
EAL: Detected 80 lcore(s)
EAL: Detected 2 NUMA nodes
EAL: Multi-process socket
On Wed, Jul 29, 2020 at 10:51 AM Balaji K N wrote:
> We are using OVS 2.12.0 with DPDK 18.11.2 release on Ubuntu 16.04 LTS. We do
> observe long initialization time for EAL init ( ~10 seconds for EAL memory
> initialization).
>
> Below is our hardware and memory configuration
> Hardware
On Tue, Jul 28, 2020 at 7:11 PM Yuying Zhang wrote:
>
> The ol_flags check lacks of flag for IPv6 which causes checksum
> flag configuration error while IPv6/TCP TSO packet is sent.
> This patch fixes the issue by adding PKT_TX_TCP_SEG flag.
>
> Fixes: 520059a41aa9 ("net: check fragmented headers
On 29-Jul-20 9:52 AM, David Marchand wrote:
On Wed, Jul 29, 2020 at 10:51 AM Balaji K N wrote:
We are using OVS 2.12.0 with DPDK 18.11.2 release on Ubuntu 16.04 LTS. We do
observe long initialization time for EAL init ( ~10 seconds for EAL memory
initialization).
Below is our hardware and m
On 7/29/20 10:43 AM, Matan Azrad wrote:
> Hi Maxime
>
> From: Maxime Coquelin:
>> On 7/28/20 9:03 PM, Matan Azrad wrote:
>>>
>>>
>>> From: Maxime Coquelin:
At .new_device() time, only the first vring pair is now ready, other
vrings are consfigured later.
Problem is that when
This series aims at fixing the regressions reported by Intel QE.
I managed to reproduce the issues, and this series fixes them.
The two first patches fix the performance regression. They have
been tested by intel QE which confirms the fix.
In this v3, only change is in the third patch, which aims
Now that the vhost library saves the guest notifications
enablement value in its virtqueues metadata, it is not
necessary to do it in the vring_state_changed callback.
One effect of the patch is also to prevent possible
deadlock happening in vhost library.
Fixes: 604052ae5395 ("net/vhost: support
At .new_device() time, only the first vring pair is
now ready, other vrings are consfigured later.
Problem is that when application will setup and enable
interrupts, only the first queue pair Rx interrupt will
be enabled.
This patches fixes the issue by setting the number of
max interrupts to the
If rte_vhost_enable_guest_notification is called before
the virtqueue is ready, the configuration is lost.
This patch fixes this by saving the guest notification
enablement value requested by the application, and apply
it before the virtqueue is made ready to the application.
Fixes: 604052ae5395
On 27-Jul-20 8:20 PM, Stephen Hemminger wrote:
Announce upcoming changes related to master/slave in reference
to lcore.
Signed-off-by: Stephen Hemminger
---
doc/guides/rel_notes/deprecation.rst | 17 +
1 file changed, 17 insertions(+)
diff --git a/doc/guides/rel_notes/deprec
On 27-Jul-20 8:20 PM, Stephen Hemminger wrote:
Correct terminolgy here is primary process.
This is a bug in original doc.
Fixes: fc1f2750a3ec ("doc: programmers guide")
Cc: bernard.iremon...@intel.com
Signed-off-by: Stephen Hemminger
---
Acked-by: Anatoly Burakov
--
Thanks,
Anatoly
Hi Slava,
Thanks for your analysis. Some comments inline.
> -Original Message-
> From: Slava Ovsiienko
> Sent: Wednesday, July 29, 2020 4:08 PM
> To: Phil Yang
> Cc: Matan Azrad ; Raslan Darawsheh
> ; tho...@monjalon.net; ferruh.yi...@intel.com;
> Honnappa Nagarahalli ; nd
> ; dev@dpdk.
On Tue, Jul 28, 2020 at 12:59:22PM -0700, Stephen Hemminger wrote:
> On Tue, 28 Jul 2020 11:24:58 +0100
> Bruce Richardson wrote:
>
> > On Thu, Jul 02, 2020 at 10:28:52AM -0700, Stephen Hemminger wrote:
> > > The maximum number of metrics is hardcoded at 256.
> > > This severely limits the useful
Hi Dikshant,
Looks like the custom Makefile log is quite different in passing DPDK CFLAGS
and LDFLAGS. Also here are couple of surprises for me
1. Unable to find `make -n` logs
2. presence of g++ is present in each line
3. unable to find include option
4. request was to run `make -n` and cro
Couple more request,
1. please avoid ` NOT FROM AIRSPAN - Caution - External ` headers & banners.
2. If possible, use `snip` or `snipped` to remove clutter and bring foucs
Snipped
> Hi Dikshant,
>
> Looks like the custom Makefile log is quite different in passing DPDK CFLAGS
> and LDFLAGS. Al
On Wed, Jul 29, 2020 at 11:56 AM Balaji K N wrote:
>
> Hello,
>
> I tried by disabling mlockall and not do see long time for EAL init and is
> done quickly. Thanks for help.
>
> ovs-vswitchd unix:/var/run/openvswitch/db.sock -vconsole:emer -vsyslog:err
> -vfile:info --no-chdir --log-file=/var/lo
On 7/29/2020 9:54 AM, David Marchand wrote:
> On Tue, Jul 28, 2020 at 7:11 PM Yuying Zhang wrote:
>>
>> The ol_flags check lacks of flag for IPv6 which causes checksum
>> flag configuration error while IPv6/TCP TSO packet is sent.
>> This patch fixes the issue by adding PKT_TX_TCP_SEG flag.
>>
>>
> -Original Message-
> From: Wang, Haiyue
> Sent: Wednesday, July 29, 2020 15:51
> To: dev@dpdk.org; Yang, Qiming ; Zhang, Qi Z
>
> Cc: Wang, Yinan ; Xu, Ting ;
> Wang, Haiyue ; sta...@dpdk.org
> Subject: [PATCH v1] net/ice: calculate TCP header size for offload
>
> The ice needs the
Add deprecation note for making changes in data structures and APIs
in order to allow dynamic configuration of subport bandwidth profile.
These changes are aligned as suggested in the RFC[1].
https://mails.dpdk.org/archives/dev/2020-July/175161.html
Signed-off-by: Savinay Dharmappa
Acked-by: Jas
From: Yuval Avnery
Following the new RegEx class.
There is a need to create a dedicated test application in order to
validate this class and PMD.
Unlike net device this application loads data from a file.
This commit introduces the new RegEx test app.
The basic app flow:
1. Configure the RegEx
From: Yuval Avnery
Following the new RegEx class.
There is a need to create a dedicated test application in order to
validate this class and PMD.
Unlike net device this application loads data from a file.
This commit introduces the new RegEx test app.
The basic app flow:
1. Configure the RegEx
On Wed, Jul 29, 2020 at 11:20 AM Maxime Coquelin
wrote:
>
> At .new_device() time, only the first vring pair is
> now ready, other vrings are consfigured later.
configured*
>
> Problem is that when application will setup and enable
> interrupts, only the first queue pair Rx interrupt will
> be e
From: Yunjian Wang
When setup tx queues, we will create a mempool for the 'gso_ctx'.
The mempool is not freed when closing tap device. If free the tap
device and create it with different name, it will create a new
mempool. This maybe cause an OOM.
Fixes: 050316a88313 ("net/tap: support TSO (TCP
Ping for review
Thanks,
Yunjian
> -Original Message-
> From: Kevin Traynor [mailto:ktray...@redhat.com]
> Sent: Wednesday, May 27, 2020 6:45 PM
> To: Burakov, Anatoly ; David Marchand
> ; wangyunjian ;
> Luca Boccassi
> Cc: dev ; Hemant Agrawal ;
> Sachin Saxena ; Lilijun (Jerry)
> ; xud
Ping for review.
Thanks,
Yunjian
> -Original Message-
> From: wangyunjian
> Sent: Friday, July 3, 2020 5:46 PM
> To: dev@dpdk.org
> Cc: jia@intel.com; Lilijun (Jerry) ; xudingke
> ; wangyunjian ;
> sta...@dpdk.org
> Subject: [dpdk-dev] [PATCH v4 1/3] eal: fix memory leak when removing
On Wed, Jul 22, 2020 at 4:13 AM Ting Xu wrote:
>
> When create softnic hash table with 16 keys, it failed on 32-bit
> environment, because the pointer field in structure rte_bucket_4_16
> is only 32 bits. Add a padding field in 32-bit environment to keep
> the structure to a multiple of 64 bytes.
29/07/2020 08:39, Hemant Agrawal:
> Hi David
>
> From: David Marchand
> >
> > Hello Hemant,
> >
> > On Mon, Jul 20, 2020 at 6:50 AM Hemant Agrawal
> > wrote:
> > > >Why dropping this codebase in DPDK instead of pulling it as a
> > dependency?
> > > [Hemant] >I don't like seeing DPDK becoming a
Signed-off-by: Raslan Darawsheh
---
doc/guides/rel_notes/release_20_08.rst | 141 +
1 file changed, 141 insertions(+)
diff --git a/doc/guides/rel_notes/release_20_08.rst
b/doc/guides/rel_notes/release_20_08.rst
index b06e39842..1bc4d631c 100644
--- a/doc/guides/rel_notes
To detect the timestamp mode configured on the NIC the mlx5
PMD uses the firmware command ACCESS_REGISTER_USER. This
command is relatively new and might be not supported by
older firmware versions and was rejected, causing annoying
messages in kernel log.
This patch adds the attribute flag check w
The testpmd application forwards data in multiple threads.
In the txonly mode the Tx timestamps must be initialized
on per thread basis to provide phase shift for the packet
burst being sent. This per thread initialization was performed
on zero value of the variable in thread local storage and
happ
Hello,
We are using OVS 2.12.0 with DPDK 18.11.2 release on Ubuntu 16.04 LTS. We do
observe long initialization time for EAL init ( ~10 seconds for EAL memory
initialization).
Below is our hardware and memory configuration
Hardware : Dell Server
Sockets(NUMA) : 2
On 7/29/20 11:20 AM, Maxime Coquelin wrote:
> At .new_device() time, only the first vring pair is
> now ready, other vrings are consfigured later.
>
> Problem is that when application will setup and enable
> interrupts, only the first queue pair Rx interrupt will
> be enabled.
>
> This patches
> -Original Message-
> From: Guo, Jia
> Sent: Tuesday, July 28, 2020 5:21 PM
> To: Zhang, Qi Z ; Yang, Qiming
> Cc: dev@dpdk.org; Su, Simei ; Guo, Jia
>
> Subject: [dpdk-dev v1] net/ice: fix gtpu teid hash
>
> Refine gtpu teid hash rule mapping for
> GTPU_IP/GTPU_EH/GTPU_DWN/GTPU_UP.
> -Original Message-
> From: David Marchand
> Sent: Wednesday, July 29, 2020 1:01 PM
> To: Xu, Ting ; Dumitrescu, Cristian
>
> Cc: dev ; dpdk stable
> Subject: Re: [dpdk-dev] [PATCH v4] lib/table: fix cache alignment issue
>
> On Wed, Jul 22, 2020 at 4:13 AM Ting Xu wrote:
> >
> > Wh
On 7/29/20 1:27 PM, David Marchand wrote:
> On Wed, Jul 29, 2020 at 11:20 AM Maxime Coquelin
> wrote:
>>
>> At .new_device() time, only the first vring pair is
>> now ready, other vrings are consfigured later.
>
> configured*
>
>>
>> Problem is that when application will setup and enable
>> i
26/07/2020 21:19, Akhil Goyal:
> > >
> > > [Adam] The ret variable value (signed) is not returned directly, please
> > > check the
> > rest of this function in src
> > > code. This is just checked to calculate how many ops were enqueued. And
> > > if all
> > checks skip (meaning the
> > > op was
Hi Maxime,
> -Original Message-
> From: Maxime Coquelin
> Sent: Wednesday, July 29, 2020 8:54 PM
> To: dev@dpdk.org; ma...@mellanox.com; Xia, Chenbo
> ; Liu, Yong ; Wang, Yinan
>
> Cc: tho...@monjalon.net; Yigit, Ferruh ;
> david.march...@redhat.com
> Subject: Re: [PATCH v3 3/3] net/vhos
On 7/29/20 3:24 PM, Xia, Chenbo wrote:
> Hi Maxime,
>
>> -Original Message-
>> From: Maxime Coquelin
>> Sent: Wednesday, July 29, 2020 8:54 PM
>> To: dev@dpdk.org; ma...@mellanox.com; Xia, Chenbo
>> ; Liu, Yong ; Wang, Yinan
>>
>> Cc: tho...@monjalon.net; Yigit, Ferruh ;
>> david.marc
On Wed, Jul 29, 2020 at 3:14 PM Dumitrescu, Cristian
wrote:
> > Please correct me if I am wrong, but it simply means this part of the
> > table library never worked for 32-bit.
> > It seems more adding 32-bit support rather than a fix and then I
> > wonder if it has its place in rc3.
> >
>
> Funct
28/07/2020 22:14, Akhil Goyal:
> http://dpdk.org/git/next/dpdk-next-crypto
Pulled, thanks
Please be more careful on quality of QuickAssist patches.
This series aims at fixing the regressions reported by Intel QE.
I managed to reproduce the issues, and this series fixes them.
The two first patches fix the performance regression. They have
been tested by intel QE which confirms the fix.
Patch 3 aims at fixing interrupt mode.
In this v4, only
If rte_vhost_enable_guest_notification is called before
the virtqueue is ready, the configuration is lost.
This patch fixes this by saving the guest notification
enablement value requested by the application, and apply
it before the virtqueue is made ready to the application.
Fixes: 604052ae5395
Now that the vhost library saves the guest notifications
enablement value in its virtqueues metadata, it is not
necessary to do it in the vring_state_changed callback.
One effect of the patch is also to prevent possible
deadlock happening in vhost library.
Fixes: 604052ae5395 ("net/vhost: support
At .new_device() time, only the first vring pair is
now ready, other vrings are configured later.
Problem is that when application will setup and enable
interrupts, only the first queue pair Rx interrupt will
be enabled.
This patches fixes the issue by setting the number of
max interrupts to the
Hello Feifei,
On Wed, Jul 29, 2020 at 8:32 AM Feifei Wang wrote:
>
> When enqueue one element (object of type void*) to ring in the
> performance test, a pointer (the object to be enqueued) should be
> passed to rte_ring_[sp|mp]enqueue APIs, not the pointer to a table
> of void *pointers (objects
> -Original Message-
> From: David Marchand
> Sent: Wednesday, July 29, 2020 2:28 PM
> To: Dumitrescu, Cristian
> Cc: Xu, Ting ; dev ; dpdk stable
> ; Kevin Traynor ; Luca Boccassi
>
> Subject: Re: [dpdk-stable] [dpdk-dev] [PATCH v4] lib/table: fix cache
> alignment issue
>
> On Wed,
29/07/2020 13:26, Ori Kam:
> --- /dev/null
> +++ b/app/test-regex/Makefile
> @@ -0,0 +1,21 @@
> +# SPDX-License-Identifier: BSD-3-Clause
> +# Copyright 2020 Mellanox Technologies, Ltd
> +
> +include $(RTE_SDK)/mk/rte.vars.mk
> +
> +#
> +# library name
It's not a library.
You can completely drop th
Commit cc0251813277 ("net/netvsc: split send buffers from Tx
descriptors") changed the way that transmit descriptors are
allocated. They come from a single pool instead of being
individually attached to each mbuf. To find the IOVA, you need
to calculate the offset from the base of the pool.
Fixes:
On Wed, Jul 29, 2020 at 3:54 PM Dumitrescu, Cristian
wrote:
> > -Original Message-
> > From: David Marchand
> > Sent: Wednesday, July 29, 2020 2:28 PM
> > To: Dumitrescu, Cristian
> > Cc: Xu, Ting ; dev ; dpdk stable
> > ; Kevin Traynor ; Luca Boccassi
> >
> > Subject: Re: [dpdk-stable]
The current registration name has the net prefix, which is incorrect.
This commit removes the net and changes the name to be regex_mlx5.
Signed-off-by: Ori Kam
---
drivers/regex/mlx5/mlx5_regex.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/regex/mlx5/mlx5_re
1)
During power initialization the pstate cpufreq api is
not setting the initial curr_idx of pstate_power_info
to corresponding current frequency index.
Without this the idx is always 0, which is causing the
below check to pass and returns without setting the initial
min/max frequency to system ma
> -Original Message-
> From: Viacheslav Ovsiienko
> Sent: Wednesday, July 29, 2020 8:30 PM
> To: dev@dpdk.org
> Cc: ma...@mellanox.com; rasl...@mellanox.com; tho...@monjalon.net;
> ferruh.yi...@intel.com; Phil Yang
> Subject: [PATCH v2] app/testpmd: fix txonly mode timestamp intitializati
29/07/2020 16:01, Ori Kam:
> The current registration name has the net prefix, which is incorrect.
> This commit removes the net and changes the name to be regex_mlx5.
>
> Signed-off-by: Ori Kam
> ---
> drivers/regex/mlx5/mlx5_regex.c | 6 +++---
> 1 file changed, 3 insertions(+), 3 deletions(-)
17/07/2020 22:18, Long Li:
> From: Long Li
>
> rte_smp_mb() uses the same locked ADD as the in-kernel vmbus driver,
> and it has slightly performance improvement over rte_mb().
>
> Signed-off-by: Long Li
Applied, thanks
On Wed, Jul 29, 2020 at 4:10 PM Thomas Monjalon wrote:
>
> 29/07/2020 16:01, Ori Kam:
> > The current registration name has the net prefix, which is incorrect.
> > This commit removes the net and changes the name to be regex_mlx5.
> >
It was offlist, but
Reported-by: David Marchand
> > Signed-
Hi, David
> -邮件原件-
> 发件人: David Marchand
> 发送时间: 2020年7月29日 21:48
> 收件人: Feifei Wang
> 抄送: Honnappa Nagarahalli ; Konstantin
> Ananyev ; Gavin Hu ;
> Olivier Matz ; dev ; nd
> ; dpdk stable
> 主题: Re: [dpdk-dev] [PATCH v1 2/2] test/ring: fix wrong param passed to the
> enqueue APIs
>
>
> -Original Message-
> From: Maxime Coquelin
> Sent: Wednesday, July 29, 2020 9:36 PM
> To: dev@dpdk.org; ma...@mellanox.com; Xia, Chenbo
> ; Liu, Yong ; Wang, Yinan
>
> Cc: tho...@monjalon.net; Yigit, Ferruh ;
> david.march...@redhat.com; Maxime Coquelin
>
> Subject: [PATCH v4 3/3] ne
On Wed, Jul 29, 2020 at 4:16 PM Feifei Wang wrote:
> > Are we missing a check in the UT so that dequeued object is what had been
> > enqueued?
> >
> >
> Dequeue is not necessary to change because the param defined in
> rte_ring_dequeue
> is different from that in rte_ring_enqueue:
> rte_ring_enqu
On 7/29/20 3:12 PM, Chenbo Xia wrote:
> Setting the flags of tapfd may fail and the return value
> should be checked.
>
> Coverity issue: 140739
> Fixes: e3b434818bbb ("net/virtio-user: support kernel vhost")
> Cc: sta...@dpdk.org
>
> Signed-off-by: Chenbo Xia
> ---
> drivers/net/virtio/virt
This is proposal to move AES-GMAC algorithm to AEAD set
of algorithms. It is however not 100% conformant GMAC as instead of aad pointer
data to be authenticated is passed normally and aead.data.length field
is used to specify length of data to be authenticated.
Reason behind this move is that GMAC
On 7/29/20 4:04 AM, Patrick Fu wrote:
> Async copy fails when single ring buffer vector is splited on multiple
> physical pages. This happens because current hpa address translation
> function doesn't handle multi-page buffers. A new gpa to hpa address
> conversion function, which returns the hp
https://bugs.dpdk.org/show_bug.cgi?id=518
Bug ID: 518
Summary: Disabling a VF with XL710 still sees the traffic and
the link is still high
Product: DPDK
Version: 18.05
Hardware: x86
OS: Linux
Sta
mlx5_nl_mac_addr_flush should flush all allocated MAC
addresses.
The MAC addresses array size should be of size
MLX5_MAX_MAC_ADDRESSES, but currently we return without
flushing the addresses if size is MLX5_MAX_MAC_ADDRESSES.
This was fixed by not allowing an array larger than
MLX5_MAX_MAC_ADDRES
Hi Hemant,
On 29/07/2020 07:39, Hemant Agrawal wrote:
> Hi David
>
>> -Original Message-
>> From: David Marchand
>> Sent: Tuesday, July 28, 2020 7:12 PM
>> To: Hemant Agrawal
>> Cc: Thomas Monjalon ; Sachin Saxena
>> ; dev@dpdk.org; Ferruh Yigit
>> ; techbo...@dpdk.org
>> Subject: Re: [
Hello all,
I was wondering what everyone's thoughts on doing both userspace testing
and unprivileged testing of dpdk applications is. DTS currently runs all
commands on the tester and the dut as the root user. Please correct me if
I'm wrong, but I was under the assumption that most applications wr
Hi All,
I would give bit more introduction to this change:
Right now AES-GMAC is auth only algorithm (previously it was cipher+auth -> GCM
+ GMAC),
but since it is variant of AES-GCM implementation it should probably be AEAD
right now (people often wondering why at all it is auth instead of AEAD
Enumerators RTE_CRYPTO_CIPHER_LIST_END, RTE_CRYPTO_AUTH_LIST_END,
RTE_CRYPTO_AEAD_LIST_END will be removed to prevent some problems
that may arise when adding new algorithms.
Signed-off-by: Arek Kusztal
---
doc/guides/rel_notes/deprecation.rst | 6 ++
1 file changed, 6 insertions(+)
diff --
> -Original Message-
> From: David Marchand
> Sent: Wednesday, July 29, 2020 3:00 PM
> To: Dumitrescu, Cristian
> Cc: Xu, Ting ; dev ; dpdk stable
> ; Kevin Traynor ; Luca Boccassi
>
> Subject: Re: [dpdk-stable] [dpdk-dev] [PATCH v4] lib/table: fix cache
> alignment issue
>
> On Wed,
Hi All,
This is proposal to remove list_end enumerators from algorithms enums.
I do not expect many changes in current list of algorithms but it may happen
(ChachaPoly in 20.02, GMAC move to AEAD proposal) so relying on list_end
enumerator may be incorrect approach as this value may change acros
On 7/29/20 3:12 PM, Chenbo Xia wrote:
> Setting the flags of tapfd may fail and the return value
> should be checked.
>
> Coverity issue: 140739
> Fixes: e3b434818bbb ("net/virtio-user: support kernel vhost")
> Cc: sta...@dpdk.org
>
> Signed-off-by: Chenbo Xia
> ---
> drivers/net/virtio/virt
On 7/29/20 3:36 PM, Maxime Coquelin wrote:
> This series aims at fixing the regressions reported by Intel QE.
> I managed to reproduce the issues, and this series fixes them.
>
> The two first patches fix the performance regression. They have
> been tested by intel QE which confirms the fix.
>
Hi Vipin,
I tried using `-Wl,--whole-archive` and `-Wl,--no-whole-archive ` option with
my necessary libraries but it does not seem to help as well.
Below is the makefile log for my app:
g++ -shared -Wl,--export-dynamic packet_generator.o
-L/mnt/data/dchitkara/DPDK_2020_01_30_x86/x86_64-nati
On 7/29/20 4:04 AM, Patrick Fu wrote:
> Async copy fails when single ring buffer vector is splited on multiple
> physical pages. This happens because current hpa address translation
> function doesn't handle multi-page buffers. A new gpa to hpa address
> conversion function, which returns the hp
Hi Vipin,
Here is full log with include option and build with make -n option from master
makefile as well:
make[2]: Entering directory
`/mnt/data/dchitkara/PHY5G/Prototype/NR_5G_SIM/Tests/COMMON/PACKET_GENERATOR'
echo ./packet_generator.cc -msse4.1 -I../../../COMMON/Sys_API/Math_API/
-I../.
29/07/2020 04:14, Yuval Avnery:
> Free sq check had a bug, causing jobs to overwrite.
Reworded with Ori's help:
regex/mlx5: fix overrun on enqueueing
When enqueueing a buffer the PMD check if there is room
in its send queue (SQ).
The current implementation did not take into a
Hi,
> -Original Message-
> From: dev On Behalf Of Yuval Avnery
> Sent: Tuesday, July 28, 2020 8:51 PM
> To: Matan Azrad ; Shahaf Shuler
> ; Slava Ovsiienko
> Cc: Thomas Monjalon ; dev@dpdk.org; Yuval
> Avnery ; Ori Kam
> Subject: [dpdk-dev] [PATCH v1] common/mlx5: fix set regex register
Hi,
> -Original Message-
> From: Viacheslav Ovsiienko
> Sent: Wednesday, July 29, 2020 3:29 PM
> To: dev@dpdk.org
> Cc: Matan Azrad ; Raslan Darawsheh
> ; Dekel Peled
> Subject: [PATCH] common/mlx5: fix user mode register access command
>
> To detect the timestamp mode configured on the
> -邮件原件-
> 发件人: David Marchand
> 发送时间: 2020年7月29日 22:21
> 收件人: Feifei Wang
> 抄送: Honnappa Nagarahalli ; Konstantin
> Ananyev ; Gavin Hu ;
> Olivier Matz ; dev ; nd
> ; dpdk stable
> 主题: Re: [dpdk-dev] [PATCH v1 2/2] test/ring: fix wrong param passed to the
> enqueue APIs
>
> On Wed, J
Hi,
> -Original Message-
> From: Shiri Kuzin
> Sent: Wednesday, July 29, 2020 5:29 PM
> To: dev@dpdk.org
> Cc: Matan Azrad ; Raslan Darawsheh
> ; Ori Kam ; Slava Ovsiienko
> ; sta...@dpdk.org
> Subject: [PATCH] common/mlx5: fix MAC addresses flush
>
> mlx5_nl_mac_addr_flush should flush
On Wed, Jul 29, 2020 at 04:46:51PM +0200, Arek Kusztal wrote:
> Enumerators RTE_CRYPTO_CIPHER_LIST_END, RTE_CRYPTO_AUTH_LIST_END,
> RTE_CRYPTO_AEAD_LIST_END will be removed to prevent some problems
> that may arise when adding new algorithms.
>
> Signed-off-by: Arek Kusztal
Since these seem to c
> -Original Message-
> From: Kusztal, ArkadiuszX
> Sent: Wednesday, July 29, 2020 3:47 PM
> To: dev@dpdk.org
> Cc: akhil.go...@nxp.com; Trahe, Fiona ;
> ano...@marvell.com;
> shal...@marvell.com; Doherty, Declan ; Zhang, Roy
> Fan
> ; Ananyev, Konstantin
> ; Kusztal, ArkadiuszX
>
>
On Wed, Jul 29, 2020 at 4:47 PM Arek Kusztal
wrote:
>
> Enumerators RTE_CRYPTO_CIPHER_LIST_END, RTE_CRYPTO_AUTH_LIST_END,
> RTE_CRYPTO_AEAD_LIST_END will be removed to prevent some problems
> that may arise when adding new algorithms.
How does it cohabitate with Ferruh notice?
Is it a complement?
On 7/29/2020 3:07 PM, Phil Yang wrote:
>> -Original Message-
>> From: Viacheslav Ovsiienko
>> Sent: Wednesday, July 29, 2020 8:30 PM
>> To: dev@dpdk.org
>> Cc: ma...@mellanox.com; rasl...@mellanox.com; tho...@monjalon.net;
>> ferruh.yi...@intel.com; Phil Yang
>> Subject: [PATCH v2] app/te
Hi David,
> -Original Message-
> From: David Marchand
> Sent: Wednesday, July 29, 2020 4:24 PM
> To: Kusztal, ArkadiuszX
> Cc: dev ; Akhil Goyal ; Trahe, Fiona
> ;
> Anoob Joseph ; shal...@marvell.com; Doherty, Declan
> ; Zhang, Roy Fan ;
> Ananyev, Konstantin
>
> Subject: Re: [dpdk-d
On 29-Jul-20 3:34 PM, Owen Hilyard wrote:
Hello all,
I was wondering what everyone's thoughts on doing both userspace testing
and unprivileged testing of dpdk applications is. DTS currently runs all
commands on the tester and the dut as the root user. Please correct me if
I'm wrong, but I was un
On 7/28/20 12:29 PM, Olivier Matz wrote:
> Hi,
>
> On Tue, Jul 28, 2020 at 08:55:31AM +, Yuying Zhang wrote:
>> The ol_flags check lacks of PKT_TX_IPV6 which causes checksum
>> flag configuration error while IPv6/TCP TSO packet is sent.
>> This patch fixes the issue using PKT_TX_OFFLOAD_MASK.
On Wed, Jul 29, 2020 at 8:31 AM Feifei Wang wrote:
>
> When enqueue one element to the ring, the param "obj" should be the
> object to be added into the ring. The object is of type void*.
I understand void * as a pointer to an object you don't know the type of.
I would keep the current descriptio
1 - 100 of 143 matches
Mail list logo